Fig. 4From: In-silico performance, validation, and modeling of the Nanostring Banff Human Organ transplant gene panel using archival data from human kidney transplantsMean Probability vs Disparity. Using the regression in 3A, the regression creates a column for the probability for each of the six diagnoses for each sample. The highest probability is assigned as most likely DX. The disparities between the annotated DX and the most likely DX creates the confusion matrix. Left = Disparity: DX does not equal most likely DX. Right = No disparity: DX = most likely DXBack to article page